- Pricing
- Not published
- Released
- 1mo ago
Cost
Grok Voice Transcribe 2.0 is SpaceXSI's speech-to-text model, built on the audio foundation model behind Grok Voice. In its launch announcement, the maker says that across its real-world evaluations the model is twice as accurate as Grok Voice Transcribe 1.0 at the same price. Trained on a dataset of live, noisy, multilingual audio recorded across diverse environments and refined with post-training, it is described as one of the most accurate transcription models for speech in real-world settings.
How it compares
Additional source evidence
- Source model
- xai/grok-voice-transcribe-2.0
- Source family
- grok
- Source type
- transcription
- Last updated
- 2026-09-17
- Model context
- —
- Model output limit
- —
- Open weights
- No
- File attachments
- Yes
- Reasoning
- No
- Tool calling
- No
- Temperature control
- No
Complete source record (JSON)
{
"id": "xai/grok-voice-transcribe-2.0",
"name": "Grok Voice Transcribe 2.0",
"description": "Speech-to-text model with word-level timestamps, speaker diarization, multichannel audio, and streaming",
"family": "grok",
"type": "transcription",
"last_updated": "2026-09-17",
"attachment": true,
"reasoning": false,
"tool_call": false,
"temperature": false,
"modalities": {
"input": [
"audio"
],
"output": [
"text"
]
},
"limit": {
"context": 0,
"output": 0
},
"release_date": "2026-09-17",
"open_weights": false
}Frequently asked questions
Quality and benchmarks
The closest alternatives are Suno v6 and Suno v6-mini by Suno, plus Sonic 3.6 by Cartesia. They are matched on model kind and release date, with no comparable price.
Suno v6Grok Voice Transcribe 2.0 vs Suno v6Suno v6-miniGrok Voice Transcribe 2.0 vs Suno v6-miniSonic 3.6Grok Voice Transcribe 2.0 vs Sonic 3.6
Licensing and access
No, Grok Voice Transcribe 2.0 is closed.
Basics
Grok Voice Transcribe 2.0 was made by xAI and released on September 17, 2026.
Generated from Vertical Tabs data, updated November 2, 2026.
Discussion
No comments yet
Be the first to share your thoughts.